A blood glucose information management system for blood glucose dynamic monitoring

Abstract

This invention relates to the technical field of blood glucose monitoring and discloses a blood glucose information management system for dynamic blood glucose monitoring, comprising a data acquisition module, a data processing module, an intelligent adjustment module, a database module, and a user interaction module. The data acquisition module acquires the user's blood glucose data, exercise data, and microenvironment data. The data processing module calculates the user's blood glucose fluctuation data and determines the user's exercise status. The intelligent adjustment module dynamically adjusts the blood glucose monitoring frequency and corrects the user's blood glucose data. The database module records the user's blood glucose data and basic user data. The user interaction module provides abnormal blood glucose warnings to the user based on the user's blood glucose data and the blood glucose warning threshold. This invention effectively improves the dynamic adaptability of blood glucose monitoring and can meet the blood glucose monitoring needs of different patients in different states.

Description

Technical Field

[0001] This invention relates to the technical field of blood glucose monitoring, and specifically to a blood glucose information management system for dynamic blood glucose monitoring. Background Technology

[0002] Traditional blood glucose monitoring methods primarily rely on patients manually measuring blood glucose using a meter, a method with significant limitations. Patients need to frequently prick their fingers to collect blood samples, increasing the risk of infection. Furthermore, manual recording of blood glucose data is prone to errors and omissions, hindering long-term data tracking and analysis. The introduction of IoT technology has brought some improvements to blood glucose monitoring. Some existing IoT-based blood glucose monitoring systems can achieve automatic and continuous blood glucose monitoring and automatic transmission of blood glucose data, sending data to relevant devices or platforms in real time. However, existing systems still have shortcomings in several key aspects.

[0003] The collection of microenvironmental data is a weak link in existing systems. Environmental factors such as humidity and sweat concentration at the skin can interfere with the accuracy of blood glucose sensor measurements. Current blood glucose information management systems rarely consider these factors, reducing measurement reliability. Regarding the adjustment of blood glucose monitoring frequency, existing systems lack intelligence and personalization. Existing solutions typically use a fixed sampling frequency, which leads to excessive data collection in some cases, increasing the burden on patients and the energy consumption of the equipment, while in other cases, the sampling frequency is too low, causing the omission of important blood glucose changes. Furthermore, existing blood glucose information management systems are also rather crude in setting blood glucose warning thresholds. Most use uniform standards or simple classifications to set thresholds, without fully considering individual patient differences; this makes blood glucose warnings inaccurate, prone to false alarms or missed alarms, and unable to meet patients' personalized blood glucose monitoring needs.

[0004] For example, patent application CN106885912A discloses a blood glucose test data management method, device, and blood glucose meter. This method includes: acquiring a first instruction input by a user, the first instruction instructing a blood glucose test under a blood glucose standard triggered by the first instruction for the user type; testing the blood glucose level in collected blood samples to obtain a blood glucose value; comparing the obtained blood glucose value with the blood glucose standard triggered by the first instruction for the user type to obtain a blood glucose value comparison result; and displaying the blood glucose value and the blood glucose value comparison result. This allows for accurate display of blood glucose levels in users of different user types, improving the effectiveness of blood glucose monitoring and enabling users to more effectively adjust their diet and exercise to maintain good health.

[0005] For example, patent application CN119064586A discloses a method and system for monitoring blood glucose data in the endocrinology department. This method generates a first set of fault parameters for the blood glucose monitoring device by evaluating the storage environment parameters of the blood glucose monitoring device, analyzes the performance parameters of the blood glucose monitoring device to generate a second set of fault parameters, determines the data accuracy coefficient of the blood glucose monitoring device, and generates a third set of fault parameters, thereby achieving comprehensive monitoring of the blood glucose monitoring device. This monitoring and feedback of fault data from the blood glucose monitoring device helps to quickly identify and locate the specific types of problems existing in the blood glucose monitoring device, provides a scientific basis for the maintenance of the blood glucose monitoring device, and ensures the accuracy and continuity of blood glucose data monitoring results.

[0006] All of the above technical solutions suffer from the problems mentioned in the background: they do not fully consider individual differences among patients and cannot meet patients' personalized blood glucose monitoring needs.

[0007] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide a blood glucose information management system for dynamic blood glucose monitoring, improve the accuracy of blood glucose measurement, and adapt to the blood glucose monitoring needs of different patients in different states.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0010] A blood glucose information management system for dynamic blood glucose monitoring includes a data acquisition module, a data processing module, an intelligent adjustment module, a database module, and a user interaction module; wherein:

[0011] The data acquisition module periodically acquires the user's blood glucose data based on the set monitoring frequency; the data acquisition module is also used to collect the user's exercise data and microenvironment data.

[0012] The data processing module calculates the user's blood glucose fluctuation data based on the user's historical blood glucose data, and determines the user's exercise status based on the exercise data;

[0013] The intelligent adjustment module dynamically adjusts the blood glucose monitoring frequency based on the blood glucose fluctuation data and exercise status, and corrects the user's blood glucose data based on the microenvironment data.

[0014] The database module is used to record the user's blood glucose data and the user's basic data; the user's basic data is used to set the user's blood glucose warning threshold.

[0015] The user interaction module provides abnormal blood glucose warnings to users based on their blood glucose data and the blood glucose warning threshold.

[0016] As a preferred embodiment of the blood glucose information management system for dynamic blood glucose monitoring according to the present invention, the data acquisition module includes a blood glucose data unit, a motion sensing unit, and a microenvironment sensing unit; wherein the blood glucose data unit acquires the user's blood glucose data periodically based on the monitoring frequency;

[0017] The motion sensing unit is used to collect the user's motion data; the motion data includes acceleration and heart rate; wherein, the acceleration is collected based on an acceleration sensor configured in the motion sensing unit; and the heart rate is collected based on a heart rate sensor configured in the motion sensing unit.

[0018] The microenvironment sensing unit is used to collect microenvironment data; the microenvironment data includes ambient humidity and sweat concentration; wherein, the ambient humidity is the relative humidity of the air at the skin, collected by a humidity sensor configured in the microenvironment sensing unit; the sweat concentration is expressed as the sodium ion concentration on the skin surface, collected by a sweat component sensor configured in the microenvironment sensing unit.

[0019] As a preferred embodiment of the blood glucose information management system for dynamic blood glucose monitoring according to the present invention, the data processing module includes a blood glucose monitoring unit; the blood glucose monitoring unit is used to calculate the user's blood glucose fluctuation data; the blood glucose fluctuation data includes the mean blood glucose and the standard deviation of blood glucose; wherein, the mean blood glucose is the average value of the user's blood glucose data over the past m hours; and the standard deviation of blood glucose is the standard deviation of the user's blood glucose data over the past m hours.

[0020] In a preferred embodiment of the blood glucose information management system for dynamic blood glucose monitoring according to the present invention, the data processing module further includes a motion state unit; the motion state unit is configured with a motion recognition strategy for determining the user's motion state; the motion recognition strategy is specifically as follows:

[0021] Continuously collect the user's acceleration and heart rate over n minutes; calculate the mean and standard deviation of the user's acceleration over n minutes;

[0022] The motion state unit is configured with a first heart rate threshold and a second heart rate threshold, as well as an acceleration threshold and an acceleration change threshold; if the user's heart rate is less than the first heart rate threshold and the average acceleration is less than the acceleration threshold, then the user's motion state is a stationary state.

[0023] If a user's heart rate is not less than a first heart rate threshold and less than a second heart rate threshold, and the acceleration is not less than the acceleration threshold, then the user's movement state is walking.

[0024] If the user's heart rate is not less than the second heart rate threshold and the standard deviation of acceleration is greater than the acceleration change threshold, then the user's exercise state is a state of intense exercise.

[0025] As a preferred embodiment of the blood glucose information management system for dynamic blood glucose monitoring according to the present invention, the data processing module further includes a data integration unit;

[0026] The data integration unit is used to integrate the user's basic data, which includes age, gender, height, weight, specific medical history, exercise frequency, and historical blood glucose data.

[0027] The data integration unit integrates users' basic data, including cleaning the user's basic data and encoding the basic data into feature vectors.

[0028] In a preferred embodiment of the blood glucose information management system for dynamic blood glucose monitoring according to the present invention, the intelligent adjustment module includes a monitoring and adjustment unit; the monitoring and adjustment unit is configured with a frequency adjustment strategy for dynamically adjusting the blood glucose monitoring frequency; the frequency adjustment strategy is specifically as follows:

[0029] Set the blood glucose threshold and blood glucose fluctuation threshold; set the safe sampling frequency, basic sampling frequency, sensitive sampling frequency, and maximum sampling frequency;

[0030] If the mean blood glucose level is greater than the blood glucose threshold or the standard deviation of blood glucose is greater than the blood glucose fluctuation threshold, then the blood glucose monitoring frequency is set to the sensitive sampling frequency.

[0031] If the mean blood glucose level is greater than the blood glucose threshold and the standard deviation of blood glucose is greater than the blood glucose fluctuation threshold, then the blood glucose monitoring frequency is set to the maximum sampling frequency.

[0032] If the mean blood glucose level is not greater than the blood glucose threshold and the standard deviation of blood glucose is not greater than the blood glucose fluctuation threshold, the blood glucose monitoring frequency is set to the safe sampling frequency if the user is at rest; the blood glucose monitoring frequency is set to the basic sampling frequency if the user is walking; and the blood glucose monitoring frequency is set to the maximum sampling frequency if the user is engaged in strenuous exercise.

[0033] If the blood glucose monitoring frequency changes, the monitoring and adjustment unit will send the blood glucose monitoring frequency to the blood glucose data unit.

[0034] In a preferred embodiment of the blood glucose information management system for dynamic blood glucose monitoring according to the present invention, the intelligent adjustment module further includes a blood glucose correction unit; the blood glucose correction unit is configured with a blood glucose correction model for correcting the user's blood glucose data; the equation of the blood glucose correction model is as follows:

[0035] Gc =G r ·(1+k1·(H-H1)·α1-k2·(H2-H)·α2)·(1+w·(N-N1)·β);

[0036] Among them, G c This indicates the corrected blood glucose data; G r This represents the raw blood glucose data measured by the blood glucose data unit; H represents the ambient humidity; N represents the sweat concentration; H1 represents the first threshold of ambient humidity; H2 represents the second threshold of ambient humidity; N1 represents the sweat concentration threshold.

[0037] α1 represents the first regulating factor of ambient humidity. When H is greater than H1, α1 takes the value of 1; otherwise, α1 takes the value of 0. α2 represents the second regulating factor of ambient humidity. When H is less than H2, α2 takes the value of 1; otherwise, α2 takes the value of 0. β represents the regulating factor of sweat concentration. When N is greater than N1, β takes the value of 1; otherwise, β takes the value of 0. k1, k2, and w are all weighting coefficients, and their values ​​are determined through parameter fitting.

[0038] As a preferred embodiment of the blood glucose information management system for dynamic blood glucose monitoring according to the present invention, the intelligent adjustment module further includes a threshold setting unit; the threshold setting unit is configured with a threshold calculation model for calculating the user's blood glucose warning threshold; the threshold calculation model is any one of support vector machine, decision tree, neural network model, and cluster analysis model; the input of the threshold setting unit is the feature vector of the user's basic data, and the output includes a first blood glucose threshold and a second blood glucose threshold; wherein, the first blood glucose threshold is the fasting blood glucose threshold; and the second blood glucose threshold is the blood glucose threshold within 2 hours after a meal.

[0039] In a preferred embodiment of the blood glucose information management system for dynamic blood glucose monitoring described in this invention, the user interaction module provides abnormal blood glucose alerts to the user as follows:

[0040] If, within M consecutive days, the user's fasting blood glucose level exceeds the first blood glucose threshold or the cumulative number of times the user's blood glucose level within 2 hours after a meal exceeds the second blood glucose threshold, a routine blood glucose warning will be sent to the user.

[0041] If a user's fasting blood glucose level is higher than the first blood glucose threshold or their blood glucose level within 2 hours after a meal is higher than the second blood glucose threshold within 2 consecutive hours, an emergency blood glucose warning will be sent to the user.

[0042] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0043] By acquiring blood glucose, exercise, and microenvironment data through the data acquisition module, a comprehensive understanding of the factors affecting blood glucose can be obtained. In particular, the collection of microenvironment data and the use of the blood glucose correction model in the blood glucose correction unit to correct the blood glucose data can effectively improve the accuracy of blood glucose measurement and reduce measurement errors caused by environmental factors.

[0044] Based on blood glucose fluctuation data and activity levels, the system dynamically adjusts the blood glucose monitoring frequency using a frequency adjustment strategy within the monitoring and regulation unit. This avoids the drawbacks of a fixed sampling frequency, reducing unnecessary data collection while ensuring no crucial information is missed. It can adapt to the blood glucose monitoring needs of different patients in different states, thus improving monitoring efficiency.

[0045] Using a threshold calculation model, a personalized blood glucose warning threshold is calculated based on the patient's age, medical history, and other basic data. This includes fasting blood glucose threshold and 2-hour postprandial blood glucose threshold, making blood glucose warnings more consistent with the patient's actual physiological condition and treatment goals, reducing false alarms and missed alarms, and helping patients take timely measures. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0047] Figure 1 A schematic diagram of the structure of a blood glucose information management system for dynamic blood glucose monitoring provided by the present invention;

[0048] Figure 2 This is a functional diagram of each module in a blood glucose information management system for dynamic blood glucose monitoring provided by the present invention. Detailed Implementation

[0049] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0050] This embodiment describes a blood glucose information management system for dynamic blood glucose monitoring, referring to... Figure 1 The system includes a data acquisition module, a data processing module, an intelligent adjustment module, a database module, and a user interaction module; the functions of each module are described in detail below. Figure 2 As shown.

[0051] The data acquisition module periodically acquires the user's blood glucose data based on the set monitoring frequency; the data acquisition module is also used to collect the user's exercise data and microenvironment data.

[0052] The data acquisition module includes a blood glucose data unit, a motion sensing unit, and a microenvironment sensing unit. The blood glucose data unit acquires the user's blood glucose data periodically based on the monitoring frequency. The motion sensing unit collects the user's motion data, including acceleration and heart rate. The acceleration is collected using an accelerometer configured in the motion sensing unit. The accelerometer, based on microelectromechanical systems (MEMS) technology, detects the acceleration of human motion to subsequently determine the patient's motion state, such as stillness, walking, or running.

[0053] The heart rate is collected by a heart rate sensor configured in the motion sensing unit; the heart rate sensor uses photoplethysmography (PPG) technology to measure the patient's heart rate changes, and combines acceleration data to provide a basis for adaptive sampling frequency adjustment.

[0054] The microenvironment sensing unit is used to collect microenvironment data; the microenvironment data includes ambient humidity and sweat concentration; wherein, the ambient humidity is the relative humidity of the air at the skin, which is collected based on the humidity sensor configured in the microenvironment sensing unit; the humidity sensor uses capacitive or resistive principles to detect the humidity around the skin.

[0055] The sweat concentration is expressed as the sodium ion concentration on the skin surface, collected by a sweat component sensor configured with a microenvironment sensing unit. The sweat component sensor analyzes the sodium ion concentration in sweat using techniques such as ion-selective electrodes. This microenvironmental data from the skin helps to understand the skin's microenvironmental state, thereby correcting blood glucose measurement results.

[0056] The data processing module calculates the user's blood glucose fluctuation data based on the user's historical blood glucose data, and determines the user's exercise status based on the exercise data;

[0057] The data processing module includes a blood glucose monitoring unit, an exercise status unit, and a data integration unit; wherein: the blood glucose monitoring unit is used to calculate the user's blood glucose fluctuation data; the blood glucose fluctuation data includes the mean blood glucose and the standard deviation of blood glucose; wherein, the mean blood glucose is the average value of the user's blood glucose data over the past m hours; and the standard deviation of blood glucose is the standard deviation of the user's blood glucose data over the past m hours.

[0058] The motion state unit is configured with a motion recognition strategy to determine the user's motion state; the motion recognition strategy is as follows:

[0059] Continuously collect the user's acceleration and heart rate over n minutes;

[0060] Calculate the mean and standard deviation of the user's acceleration over n minutes;

[0061] The motion state unit is configured with a first heart rate threshold and a second heart rate threshold, as well as an acceleration threshold and an acceleration change threshold. If the user's heart rate is less than the first heart rate threshold and the average acceleration is less than the acceleration threshold, then the user's motion state is a stationary state. The first heart rate threshold and the second heart rate threshold are set based on the user's resting heart rate. For example, the first heart rate threshold is 1.2 times the resting heart rate, and the second heart rate threshold is 1.4 times the resting heart rate.

[0062] If a user's heart rate is not less than the first heart rate threshold and is less than the second heart rate threshold, and the acceleration is not less than the acceleration threshold, then the user's movement state is walking; if the acceleration of the user's wrist changes periodically and the heart rate does not reach the second heart rate threshold, it can also be determined that the user is walking.

[0063] If the user's heart rate is not less than the second heart rate threshold and the standard deviation of acceleration is greater than the acceleration change threshold, then the user's exercise state is a state of intense exercise.

[0064] The data integration unit is used to integrate the user's basic data; the basic data includes age, gender, height, weight, specific medical history, exercise frequency, and historical blood glucose data; specific medical history may include, for example, diabetes, kidney disease, cardiovascular disease, etc.; historical blood glucose data includes the average blood glucose level of each day over a period of time, as well as the lowest blood glucose level when fasting and the peak blood glucose level within 2 hours after a meal.

[0065] The data integration unit integrates users' basic data, specifically including data cleaning of users' basic data and encoding the basic data into feature vectors.

[0066] The intelligent adjustment module dynamically adjusts the blood glucose monitoring frequency based on the blood glucose fluctuation data and exercise status, and corrects the user's blood glucose data based on the microenvironment data.

[0067] The intelligent adjustment module includes a monitoring and adjustment unit, a blood glucose correction unit, and a threshold setting unit; wherein: the monitoring and adjustment unit is configured with a frequency adjustment strategy for dynamically adjusting the blood glucose monitoring frequency; the frequency adjustment strategy is as follows:

[0068] Set blood glucose threshold and blood glucose fluctuation threshold;

[0069] Set the safe sampling frequency, basic sampling frequency, sensitive sampling frequency, and maximum sampling frequency. The safe sampling frequency is the lowest, for example, collecting blood glucose data once every 30 minutes. The basic sampling frequency is the regular sampling frequency, for example, collecting blood glucose data once every 15 minutes. The sensitive sampling frequency is higher than the basic sampling frequency, for example, collecting blood glucose data once every 10 minutes. The maximum sampling frequency is the most frequent, for example, collecting blood glucose data once every 5 minutes.

[0070] If the mean blood glucose level is greater than the blood glucose threshold or the standard deviation of blood glucose is greater than the blood glucose fluctuation threshold, then the blood glucose monitoring frequency is set to the sensitive sampling frequency.

[0071] If the mean blood glucose level is greater than the blood glucose threshold and the standard deviation of blood glucose is greater than the blood glucose fluctuation threshold, then the blood glucose monitoring frequency is set to the maximum sampling frequency.

[0072] If the mean blood glucose level is not greater than the blood glucose threshold and the standard deviation of blood glucose is not greater than the blood glucose fluctuation threshold, the blood glucose monitoring frequency is set to the safe sampling frequency if the user is at rest; the blood glucose monitoring frequency is set to the basic sampling frequency if the user is walking; and the blood glucose monitoring frequency is set to the maximum sampling frequency if the user is engaged in strenuous exercise.

[0073] If the blood glucose monitoring frequency changes, the monitoring and adjustment unit will send the blood glucose monitoring frequency to the blood glucose data unit.

[0074] The aforementioned frequency adjustment strategy automatically adjusts the sampling frequency of the blood glucose monitoring device based on the patient's real-time activity level, dietary intake, and past blood glucose fluctuation patterns. This reduces unnecessary data collection while ensuring that critical blood glucose information is not missed. For patients with large blood glucose fluctuations or abnormally high blood glucose levels, a higher sampling frequency is maintained under all conditions. For patients with relatively stable blood glucose levels, the sampling frequency is appropriately reduced when at rest. When the patient is exercising, the sampling frequency is further increased based on the intensity of the exercise.

[0075] The blood glucose correction unit is equipped with a blood glucose correction model for correcting the user's blood glucose data; the equation of the blood glucose correction model is as follows:

[0076] G c =G r ·(1+k1·(H-H1)·α1-k2·(H2-H)·α2)·(1+w·(N-N1)·β);

[0077] Among them, G c This indicates the corrected blood glucose data; G rThis represents the raw blood glucose data measured by the blood glucose data unit; H represents the ambient humidity; N represents the sweat concentration; H1 represents the first threshold of ambient humidity; H2 represents the second threshold of ambient humidity; N1 represents the sweat concentration threshold.

[0078] α1 represents the first regulating factor of ambient humidity. When H is greater than H1, α1 takes the value of 1; otherwise, α1 takes the value of 0. α2 represents the second regulating factor of ambient humidity. When H is less than H2, α2 takes the value of 1; otherwise, α2 takes the value of 0. β represents the regulating factor of sweat concentration. When N is greater than N1, β takes the value of 1; otherwise, β takes the value of 0. k1, k2, and w are all weighting coefficients, and their values ​​are determined through parameter fitting.

[0079] H1, H2, and N1 can be determined through parameter fitting along with weighting coefficients, or through statistical tests. For example, in a blood glucose measurement experiment under different environmental conditions, the environmental conditions are simulated by controlling the humidity in a laboratory chamber, for example, a humidity range of 20%-90% in 10% intervals. Different sweat sodium ion concentration levels are obtained by having subjects sweat at different exercise intensities. Under each set environmental condition, the subjects' blood glucose is measured multiple times simultaneously using both a reference blood glucose monitoring device and an experimental monitoring device, and the corresponding microenvironmental data, reference blood glucose data, and the original blood glucose measurement values ​​from the experimental monitoring device are recorded. The measurement data for each subject under different environmental conditions are organized and classified to ensure the accuracy and completeness of the data, removing obviously abnormal data points to obtain experimental data suitable for parameter fitting. An example of a statistical test is as follows: using statistical methods such as analysis of variance (ANOVA) to test whether there is a significant difference between the measured and actual blood glucose values ​​within different humidity ranges. The humidity range is divided into multiple candidate intervals, for example, intervals from 10% to 90% in 10% increments, and ANOVA is performed on the deviation proportion within each interval. If the mean difference in the deviation ratio between two adjacent intervals is statistically significant, then the humidity value between these two intervals is used as a threshold for environmental humidity.

[0080] High humidity environments, such as relative humidity greater than 80%, can alter the conductivity of the sensor, thus affecting the accuracy of blood glucose measurements. Conversely, low humidity environments change skin condition, further affecting measurement results. Changes in the concentration of sodium ions in sweat can also interfere with the operation of the blood glucose sensor. Increased sodium ion concentration can cause a shift in the sensor's potential, leading to higher readings. By establishing a multivariate mathematical model that comprehensively considers the combined effects of humidity and sodium ion concentration on blood glucose measurement, more accurate calibration can be achieved.

[0081] The threshold setting unit is configured with a threshold calculation model for calculating the user's blood glucose warning threshold; the threshold calculation model can be any one of support vector machine, decision tree, neural network model, or cluster analysis model; the input of the threshold setting unit is the feature vector of the user's basic data, and the output includes a first blood glucose threshold and a second blood glucose threshold; wherein, the first blood glucose threshold is the fasting blood glucose threshold; and the second blood glucose threshold is the blood glucose threshold within 2 hours after a meal.

[0082] The threshold calculation model, based on a patient's age, medical history, and other fundamental data, utilizes big data analytics and artificial intelligence algorithms to determine a personalized blood glucose threshold range for each patient. For example, the model calculates a lower fasting blood glucose threshold for younger patients in good health, and a higher threshold for older diabetic patients. By employing big data analysis and AI algorithms, a dynamic blood glucose threshold range is tailored for each patient, and this threshold information is updated in real-time to the mobile application's user interaction module. This enables accurate blood glucose anomaly detection and early warning, ensuring that blood glucose alerts are more aligned with each patient's actual physiological condition and treatment goals.

[0083] The database module is used to record the user's blood glucose data and the user's basic data; the user's basic data is used to set the user's blood glucose warning threshold.

[0084] By establishing a database to store users' blood glucose data, basic data, and corresponding exercise data and microenvironment data, a data foundation is provided for adjusting blood glucose monitoring frequency, correcting blood glucose data, and adjusting blood glucose warning thresholds. The database adopts a distributed storage architecture, such as a distributed file system or cloud database service, to ensure data security and high availability, and to quickly store and retrieve massive amounts of relevant data.

[0085] The user interaction module provides alerts for abnormal blood glucose levels based on the user's blood glucose data and the blood glucose warning threshold. Specifically:

[0086] If, over M consecutive days, a user's fasting blood glucose level exceeds the first blood glucose threshold or the cumulative number of times their blood glucose level within 2 hours after a meal exceeds the second blood glucose threshold exceeds r times, a routine blood glucose warning will be sent to the user. At this time, the system can remind the user to pay attention to recent blood glucose fluctuations, suggest that the user review their recent diet, exercise, and medication to check for any factors affecting blood glucose, and provide general dietary and exercise adjustment suggestions, such as appropriately increasing exercise and controlling carbohydrate intake. Simultaneously, the system can synchronize the warning information to healthcare professionals, who can then conduct further inquiries and provide guidance to the patient as needed.

[0087] If a user's fasting blood glucose level exceeds the first blood glucose threshold or their blood glucose level within 2 hours after a meal exceeds the second blood glucose threshold within 24 consecutive hours, an emergency blood glucose alert will be sent to the user. This ensures that the user can promptly receive the alert information. Simultaneously, the app automatically sends a message containing the user's current blood glucose data to pre-set contacts so that the user can receive timely assistance in case of severe blood glucose abnormalities. Furthermore, the app will display navigation information for nearby medical institutions, facilitating quick access to medical care.

[0088] By utilizing a cross-platform mobile application, patients can easily view real-time blood glucose data, historical blood glucose curves, and personalized health reports and recommendations. Health reports use a combination of charts and text to provide detailed interpretations of the patient's blood glucose status, trend analysis, and potential health risks, and offer targeted dietary, exercise, and medication recommendations. For example, based on the patient's blood glucose fluctuations, suitable exercise time and intensity are recommended, as well as appropriate intake of carbohydrates, protein, and fat in the diet.

[0089] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other modifications under the guidance of the present invention without departing from the spirit and scope of the present invention, and all of these modifications are within the scope of protection of the present invention.

Claims

1. A blood glucose information management system for blood glucose dynamics monitoring, characterized by: It includes a data acquisition module, a data processing module, an intelligent adjustment module, a database module, and a user interaction module; among which: The data acquisition module periodically acquires the user's blood glucose data based on the set monitoring frequency; the data acquisition module is also used to collect the user's exercise data and microenvironment data. The data processing module calculates the user's blood glucose fluctuation data based on the user's historical blood glucose data, and determines the user's exercise status based on the exercise data; The intelligent adjustment module dynamically adjusts the blood glucose monitoring frequency based on the blood glucose fluctuation data and exercise status, and corrects the user's blood glucose data based on the microenvironment data. The intelligent adjustment module includes a monitoring and adjustment unit; the monitoring and adjustment unit is configured with a frequency adjustment strategy for dynamically adjusting the blood glucose monitoring frequency; the frequency adjustment strategy is as follows: Set the blood glucose threshold and blood glucose fluctuation threshold; set the safe sampling frequency, basic sampling frequency, sensitive sampling frequency, and maximum sampling frequency; If the mean blood glucose level is greater than the blood glucose threshold or the standard deviation of blood glucose is greater than the blood glucose fluctuation threshold, then the blood glucose monitoring frequency is set to the sensitive sampling frequency. If the mean blood glucose level is greater than the blood glucose threshold and the standard deviation of blood glucose is greater than the blood glucose fluctuation threshold, then the blood glucose monitoring frequency is set to the maximum sampling frequency. If the mean blood glucose level is not greater than the blood glucose threshold and the standard deviation of blood glucose is not greater than the blood glucose fluctuation threshold, the blood glucose monitoring frequency is set to the safe sampling frequency if the user is at rest; the blood glucose monitoring frequency is set to the basic sampling frequency if the user is walking; and the blood glucose monitoring frequency is set to the maximum sampling frequency if the user is engaged in strenuous exercise. If the blood glucose monitoring frequency changes, the monitoring and adjustment unit will send the blood glucose monitoring frequency to the blood glucose data unit; The intelligent adjustment module also includes a blood glucose correction unit; the blood glucose correction unit is configured with a first threshold for ambient humidity, a second threshold for ambient humidity, and a sweat concentration threshold; the blood glucose correction unit is also configured with a blood glucose correction model, which is used to correct the user's blood glucose data; the input of the blood glucose correction model includes the raw blood glucose data measured by the blood glucose data unit, ambient humidity, and sweat concentration, and the output is the corrected blood glucose data; the equation of the blood glucose correction model is as follows: ; in, This indicates the corrected blood glucose data; This represents the raw blood glucose data measured by the blood glucose data unit; H represents the ambient humidity; N represents the sweat concentration; The first threshold representing ambient humidity; The second threshold representing ambient humidity; Indicates the threshold for sweat concentration; The first regulating factor for ambient humidity, when H is greater than 100%. , The value is 1; otherwise, The value is 0; The second regulating factor for ambient humidity, when H is less than , The value is 1; otherwise, The value is 0; The factor representing the regulating factor of sweat concentration, when N is greater than , The value is 1; otherwise, The value is 0; , Both w and are weighting coefficients; The database module is used to record the user's blood glucose data and the user's basic data; the user's basic data is used to set the user's blood glucose warning threshold. The user interaction module provides abnormal blood glucose warnings to users based on their blood glucose data and the blood glucose warning threshold.

2. The blood glucose information management system for blood glucose dynamics monitoring according to claim 1, wherein: The data acquisition module includes a blood glucose data unit, a motion sensing unit, and a microenvironment sensing unit; wherein: the blood glucose data unit acquires the user's blood glucose data periodically based on the monitoring frequency; The motion sensing unit is used to collect the user's motion data; the motion data includes acceleration and heart rate; wherein, the acceleration is collected based on an acceleration sensor configured in the motion sensing unit; and the heart rate is collected based on a heart rate sensor configured in the motion sensing unit. The microenvironment sensing unit is used to collect microenvironment data; the microenvironment data includes ambient humidity and sweat concentration; wherein, the ambient humidity is the relative humidity of the air at the skin, collected by a humidity sensor configured in the microenvironment sensing unit; the sweat concentration is expressed as the sodium ion concentration on the skin surface, collected by a sweat component sensor configured in the microenvironment sensing unit.

3. The blood glucose information management system for blood glucose dynamics monitoring according to claim 2, wherein: The data processing module includes a blood glucose monitoring unit; the blood glucose monitoring unit is used to calculate the user's blood glucose fluctuation data; the blood glucose fluctuation data includes the mean blood glucose and the standard deviation of blood glucose; wherein, the mean blood glucose is the average value of the user's blood glucose data over the past m hours; and the standard deviation of blood glucose is the standard deviation of the user's blood glucose data over the past m hours.

4. The blood glucose information management system for blood glucose dynamics monitoring according to claim 3, wherein: The data processing module further includes a motion state unit; the motion state unit is configured with a motion recognition strategy to determine the user's motion state; the motion recognition strategy is as follows: Continuously collect the user's acceleration and heart rate over n minutes; calculate the mean and standard deviation of the user's acceleration over n minutes; The motion state unit is configured with a first heart rate threshold and a second heart rate threshold, as well as an acceleration threshold and an acceleration change threshold; if the user's heart rate is less than the first heart rate threshold and the average acceleration is less than the acceleration threshold, then the user's motion state is a stationary state. If a user's heart rate is not less than a first heart rate threshold and less than a second heart rate threshold, and the acceleration is not less than the acceleration threshold, then the user's movement state is walking. If the user's heart rate is not less than the second heart rate threshold and the standard deviation of acceleration is greater than the acceleration change threshold, then the user's exercise state is a state of intense exercise.

5. The blood glucose information management system for blood glucose dynamics monitoring according to claim 4, wherein: The data processing module also includes a data integration unit; The data integration unit is used to integrate the user's basic data, which includes age, gender, height, weight, specific medical history, exercise frequency, and historical blood glucose data. The data integration unit integrates users' basic data, including cleaning the user's basic data and encoding the basic data into feature vectors.

6. The blood glucose information management system for blood glucose dynamics monitoring according to claim 5, wherein: The intelligent adjustment module also includes a threshold setting unit; the threshold setting unit is configured with a threshold calculation model for calculating the user's blood glucose warning threshold; the threshold calculation model is any one of support vector machine, decision tree, neural network model, and cluster analysis model; the input of the threshold setting unit is the feature vector of the user's basic data, and the output includes a first blood glucose threshold and a second blood glucose threshold; wherein, the first blood glucose threshold is the fasting blood glucose threshold; and the second blood glucose threshold is the blood glucose threshold within 2 hours after a meal.

7. The blood glucose information management system for blood glucose dynamics monitoring according to claim 6, wherein: The user interaction module provides alerts for abnormal blood glucose levels as follows: If, within M consecutive days, the user's fasting blood glucose level exceeds the first blood glucose threshold or the cumulative number of times the user's blood glucose level within 2 hours after a meal exceeds the second blood glucose threshold, a routine blood glucose warning will be sent to the user. If a user's fasting blood glucose level is higher than the first blood glucose threshold or their blood glucose level within 2 hours after a meal is higher than the second blood glucose threshold within 2 consecutive hours, an emergency blood glucose warning will be sent to the user.

Images